changeset 115:a6e3505227b5 draft

Uploaded
author tyty
date Tue, 14 Apr 2015 14:16:19 -0400
parents e269e4c6818e
children 62e8f7adf1ab
files get_reads/._.DS_Store get_reads/._get_read.py get_reads/._get_read.xml get_reads/._read_file.py get_reads/get_read.py get_reads/get_read.xml get_reads/read_file.py get_reads/read_file.pyc
diffstat 8 files changed, 147 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
Binary file get_reads/._.DS_Store has changed
Binary file get_reads/._get_read.py has changed
Binary file get_reads/._get_read.xml has changed
Binary file get_reads/._read_file.py has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/get_reads/get_read.py	Tue Apr 14 14:16:19 2015 -0400
@@ -0,0 +1,80 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+from Bio import SeqIO
+import os
+from read_file import *
+import random
+import string
+
+fasta_file = sys.argv[1]
+map_file = sys.argv[2]
+result_file = sys.argv[3]
+
+syspathrs = os.getcwd()
+
+os.system("samtools view -F 0xfff "+map_file+"|cut -f 3,4 > "+syspathrs+"map_info.txt") 
+
+fasta_sequences = SeqIO.parse(open(fasta_file),'fasta');
+length_seq = {};
+for seq in fasta_sequences:
+        nuc = seq.id;
+        length_seq[nuc] = len(seq.seq.tostring());
+
+
+
+mapping = {}
+transcripts = []
+
+f = open(syspathrs+"map_info.txt");
+for aline in f.readlines():
+    tline = aline.strip();
+    tl = tline.split('\t');
+    if tl[0].strip() not in transcripts:
+        transcripts.append(tl[0].strip());
+        mapping[tl[0].strip()] = [];
+
+    mapping[tl[0].strip()].append(tl[1].strip());
+
+distribution = {};
+coverage = {};
+for transcript in length_seq:
+    distribution[transcript] = [];
+    for i in range(0, length_seq[transcript]):
+        distribution[transcript].append(0);
+    sum_count = float(0);
+    if transcript in mapping:
+        for j in range(0, len(mapping[transcript])):
+            index = mapping[transcript][j];
+            #count = reads[mapping[transcript][j][0]];
+            sum_count = sum_count + 1;
+            distribution[transcript][int(index)-1] = distribution[transcript][int(index)-1] + 1;
+            coverage[transcript] = float(sum_count)/float(length_seq[transcript]);
+    else:
+        coverage[transcript] = 0
+
+        
+        
+    
+
+h = file(result_file, 'w')
+for transcript in length_seq:
+    h.write(transcript);
+    h.write('\n')
+    for i in range(0, length_seq[transcript]):
+        h.write(str(distribution[transcript][i]))
+        h.write('\t')
+    h.write('\n')
+    h.write('\n')
+
+#os.system("rm -r "+syspathrs)
+
+    
+
+f.close();
+h.close()
+
+
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/get_reads/get_read.xml	Tue Apr 14 14:16:19 2015 -0400
@@ -0,0 +1,46 @@
+<tool id="get_read_pipeline" name="Get RT Stop Counts" version="1.0">
+	<description>derives the reverse transcriptase (RT) stop count on each nucleotide from a mapped file provided by the Iterative Mapping module</description>
+	<command interpreter="python">get_read.py $lib_file $map_file $output </command>
+        <requirements>
+                <requirement type="package" version="1.61">biopython</requirement>
+                <requirement type="package" version="1.7.1">numpy</requirement>
+                <requirement type="package" version="0.1.18">samtools</requirement>
+        </requirements>
+	<inputs>
+                <param name="lib_file" type="data" format="fasta" label="Reference genome/transcriptome"/>
+		<param name="map_file" type="data" format="bam" label="Mapped file"/>
+	</inputs>
+	<outputs>
+		<data name="output" format="txt"/>
+	</outputs>
+    <tests>
+        <test>
+            <param name="lib_file" value="test.bam" />
+	        <param name="map_file" value="com_rna.txt" />
+	        <output name="output" file="get_RT_stop_test.out" /> 
+        </test>
+    </tests>
+	<help>
+
+
+**Function**
+
+Get RT Stop Counts derives the RT stop counts on each nucleotide of each transcript in the reference transcriptome based on a mapped file (.bam), typically the output from the Iterative Mapping module.
+
+-----
+
+**Input**:
+
+* 1. A mapped (.bam) file from Bowtie (or any other mapping program)
+* 2. Reference library sequences (fasta) used to map the reads to
+
+-----
+
+**Output**:
+
+A text file with reverse transcription stop counts mapped to each nucleotide (RTSC file)
+
+
+
+	</help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/get_reads/read_file.py	Tue Apr 14 14:16:19 2015 -0400
@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+
+
+
+def read_t_file(in_file):
+    f = open(in_file);
+    result = [];
+    for aline in f.readlines():
+        temp = [];
+        tline = aline.strip();
+        tl = tline.split('\t');
+        for i in range(0, len(tl)):
+            temp.append(tl[i].strip());
+        result.append(temp);
+    f.close();
+    return result;
+
+
Binary file get_reads/read_file.pyc has changed